Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Change init method from fork-server to spawn #2427

Closed
wants to merge 1 commit into from
Closed

Change init method from fork-server to spawn #2427

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions torchrec/distributed/test_utils/multi_process.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,11 @@
)


# AMD's HIP runtime doesn't seem to work with forkserver; hipMalloc will fail
# Therefore we use spawn for HIP runtime until AMD fixes the issue
_MP_INIT_MODE = "forkserver" if torch.version.hip is None else "spawn"


class MultiProcessContext:
def __init__(
self,
Expand Down Expand Up @@ -126,7 +131,7 @@ def _run_multi_process_test(
# pyre-ignore
**kwargs,
) -> None:
ctx = multiprocessing.get_context("forkserver")
ctx = multiprocessing.get_context(_MP_INIT_MODE)
processes = []
for rank in range(world_size):
kwargs["rank"] = rank
Expand All @@ -152,7 +157,7 @@ def _run_multi_process_test_per_rank(
world_size: int,
kwargs_per_rank: List[Dict[str, Any]],
) -> None:
ctx = multiprocessing.get_context("forkserver")
ctx = multiprocessing.get_context(_MP_INIT_MODE)
processes = []
for rank in range(world_size):
kwargs = {}
Expand Down
Loading